Location: Remote, based in Tbilisi, Georgia
Company
OnTarget Labs is an international software product development company creating next-generation product lines.
What you will do
•Build, deploy, and maintain NVIDIA AI Enterprise on NVIDIA-Certified systems, VMware, Kubernetes, and AWS, Azure, or GCP.
•Deliver generative AI solutions using NIM microservices, RAG and agent workflows from NVIDIA Blueprints.
•Fine-tune and apply guardrails to models with NeMo.
•Operate GPU orchestration, monitoring, security, upgrades, and MLOps for production workloads.
•Design target architectures and provide technical guidance to client engineering teams, depending on level.
•Document platforms and coach client engineers to operate them independently.
Requirements
•Bachelor's degree in Information Systems, Computer Science, or a related field.
•Excellent written and verbal English communication skills.
•Engineer: 5+ years of experience in ML engineering, MLOps, or AI infrastructure, including 2+ years working with GPU workloads.
•Architect: 8+ years of experience, including end-to-end design of enterprise AI or cloud platforms.
•Production experience with NVIDIA AI Enterprise components, especially NIM, NeMo, and Triton.
•Strong Kubernetes, container, Linux, VMware vSphere, GPU virtualization, Python, Terraform, Ansible, and Helm skills.
Nice to have
•Experience delivering an enterprise GenAI or LLM solution using RAG, fine-tuning, or agents.
Culture & Benefits
•Full-time remote work.
•Competitive compensation determined after the interview process.
•Opportunities for professional growth.
•Business trips abroad.
